Supervised Machine Learning‐Based Classification of Li−S Battery Electrolytes

Machine learning (ML) approaches have the potential to create a paradigm shift in science, especially for multi-variable problems at different levels. Modern battery R&D is an area intrinsically dependent on proper understanding of many molecular level phenomena and processes alongside evaluation application performance: energy, power, efficiency, life-length, etc. One very promising technology Li−S batteries, but polysulfide solubility electrolyte must be managed. Today, compositions concepts are evaluated, often more or less trial-and-error fashion. Herein, we show how supervised ML can applied accurately classify electrolytes priori based predicting solubility. The developed framework combined density functional theory (DFT) statistical mechanics (COSMO-RS) quantitative structure-property relationship (QSPR) model which easily extended other technologies properties.